Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Dop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    넘
    -0.07
    ViewModel
    -0.07
    -tested
    -0.06
     theirs
    -0.06
    _scaled
    -0.06
     escri
    -0.06
    -rest
    -0.06
    _DEBUG
    -0.06
     I
    -0.06
     секр
    -0.06
    POSITIVE LOGITS
     Dop
    0.08
    𝘮
    0.08
    cess
    0.07
    غان
    0.07
    اخ
    0.07
     DIN
    0.07
    rap
    0.07
    mega
    0.07
    ứ
    0.07
    ب
    0.06
    Act Density 0.002%

    No Known Activations